Post vectors

Abstract

In one embodiment, a method includes accessing a user profile associated with a user of an online social network, wherein the user profile identifies one or more topics that the user is interested in; accessing post vectors, wherein each post vector represents one of a plurality of posts, indicates one or more topics, and for each of the topics, indicates a probability that the post is related to the corresponding topic; ranking the posts based on comparisons between the user profile and the post vectors; and providing for display to the user posts based on the ranking.

What is claimed is: 
     
         1 . A method comprising:
 by one or more computing devices, accessing a user profile associated with a user of an online social network, wherein the user profile identifies one or more topics that the user is interested in;   by one or more computing devices, accessing a plurality of post vectors, wherein each post vector:
 represents one of a plurality of posts; 
 indicates one or more topics; and 
 for each of the topics, indicates a probability that the post is related to the corresponding topic; 
   by one or more computing devices, ranking the posts based on one or more comparisons between the user profile and the post vectors;   by one or more computing devices, providing for display to the user one or more of the posts based on the ranking.   
     
     
         2 . The method of  claim 1 , wherein each post vector was generated by an artificial neural network (ANN) that was trained, based on one or more training posts of one or more training pages associated with the ANN, to receive a post and then output, for each training page, a probability that the received post is related to the one or more training posts of the training page. 
     
     
         3 . The method of  claim 2 , wherein each post vector comprises an output of one or more activation functions of one or more nodes of a layer of the ANN. 
     
     
         4 . The method of  claim 1 , wherein:
 the user profile comprises a user-profile vector; and   the user-profile vector indicates one or more topics and indicates for each of the topics an intensity value representing a level of interest of the user in the topic.   
     
     
         5 . The method of  claim 4 , wherein the user-profile vector was generated based on one or more post vectors representing one or more posts that the user has interacted with. 
     
     
         6 . The method of  claim 4 , wherein:
 the one or more comparisons between the user profile and the post vectors comprises for each post vector a similarity metric between the post vectors and the user-profile vector; and   ranking the posts comprises ranking each post based on the similarity metric between the post vector representing the post and the user-profile vector.   
     
     
         7 . The method of  claim 1 , wherein a post comprises:
 one or more n-grams;   one or more videos; or   one or more images.   
     
     
         8 . The method of  claim 1 , wherein each topic corresponds to a label comprising one or more n-grams. 
     
     
         9 . The method of  claim 1 , wherein providing for display to the user one or more of the posts comprises providing posts with a rank of a least a threshold rank. 
     
     
         10 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 access a user profile associated with a user of an online social network, wherein the user profile identifies one or more topics that the user is interested in;   access a plurality of post vectors, wherein each post vector:
 represents one of a plurality of posts; 
 indicates one or more topics; and 
 for each of the topics, indicates a probability that the post is related to the corresponding topic; 
   rank the posts based on one or more comparisons between the user profile and the post vectors;   provide for display to the user one or more of the posts based on the ranking.   
     
     
         11 . The media of  claim 10 , wherein each post vector was generated by an artificial neural network (ANN) that was trained, based on one or more training posts of one or more training pages associated with the ANN, to receive a post and then output, for each training page, a probability that the received post is related to the one or more training posts of the training page. 
     
     
         12 . The media of  claim 11 , wherein each post vector comprises an output of one or more activation functions of one or more nodes of a layer of the ANN. 
     
     
         13 . The media of  claim 10 , wherein:
 the user profile comprises a user-profile vector; and   the user-profile vector indicates one or more topics and indicates for each of the topics an intensity value representing a level of interest of the user in the topic.   
     
     
         14 . The media of  claim 13 , wherein the user-profile vector was generated based on one or more post vectors representing one or more posts that the user has interacted with. 
     
     
         15 . The media of  claim 13 , wherein:
 the one or more comparisons between the user profile and the post vectors comprises for each post vector a similarity metric between the post vectors and the user-profile vector; and   ranking the posts comprises ranking each post based on the similarity metric between the post vector representing the post and the user-profile vector.   
     
     
         16 . The media of  claim 10 , wherein a post comprises:
 one or more n-grams;   one or more videos; or   one or more images.   
     
     
         17 . The media of  claim 10 , wherein each topic corresponds to a label comprising one or more n-grams. 
     
     
         18 . The media of  claim 10 , wherein providing for display to the user one or more of the posts comprises providing posts with a rank of a least a threshold rank. 
     
     
         19 . A system comprising:
 one or more processors; and   a memory coupled to the processors and comprising instructions operable when executed by the processors to cause the processors to:
 access a user profile associated with a user of an online social network, wherein the user profile identifies one or more topics that the user is interested in; 
 access a plurality of post vectors, wherein each post vector:
 represents one of a plurality of posts; 
 indicates one or more topics; and 
 for each of the topics, indicates a probability that the post is related to the corresponding topic; 
 
 rank the posts based on one or more comparisons between the user profile and the post vectors; 
 provide for display to the user one or more of the posts based on the ranking. 
   
     
     
         20 . The system of  claim 19 , wherein each post vector was generated by an artificial neural network (ANN) that was trained, based on one or more training posts of one or more training pages associated with the ANN, to receive a post and then output, for each training page, a probability that the received post is related to the one or more training posts of the training page.